© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 14432
    Prev
    Next
    INDEX
    Explanations

    concepts related to power dynamics and accountability in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.08
    osit
    -0.07
    921
    -0.07
    909
    -0.07
    into
    -0.07
    lero
    -0.06
    zion
    -0.06
    ç²¾
    -0.06
    953
    -0.06
     sho
    -0.06
    POSITIVE LOGITS
     sway
    0.11
     accountable
    0.10
     alo
    0.09
     hostage
    0.08
    ä½ı
    0.08
     steady
    0.07
    à¹Ħว
    0.07
     ä½ı
    0.07
    hold
    0.06
     hold
    0.06
    Activations Density 0.050%

    No Known Activations